© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39494
    Prev
    Next
    INDEX
    Explanations

    graphics keywords and rendering terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to computer‐graphics lighting and shading terminology (e.g. deferred, shading, light, shadow).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ּוֹ
    -1.55
    ᥬ
    -1.54
     policiais
    -1.52
     officio
    -1.48
     who
    -1.48
    歃
    -1.48
    Personen
    -1.46
     HasFactory
    -1.45
    pantalón
    -1.43
    ledning
    -1.42
    POSITIVE LOGITS
    ”
    1.54
    n
    1.52
    or
    1.48
          
    1.42
    ="
    1.41
    e
    1.36
    ↵↵
    1.33
    }
    1.32
     /*
    1.31
     zen
    1.26
    Activations Density 0.035%

    No Known Activations